A Fundamental Study on Adversarial Attacks against Deep Learning Models for Japanese Language Processing

Abstract

Recent studies have shown that Deep Neural Networks (DNNs) can cause misclassification by adversarial examples (AEs), which are input including carefully designed perturbations. This paper proposes an adversarial attack method to DNNs for Japanese language processing. The proposed method add perturbations to Japanese sentence by character type conversion, i.e., converting word notations in the sentence between kanji, hiragana, and katakana. Experimental results showed that the proposed character type conversion attack successfully made DNNs misclassify Japanese sentences.